Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Apple / Apple Foundation Models 2024

AFM On-Device (2024)

First-generation Apple language model for integrated Apple Intelligence features. This record preserves the documented 2024 generation.

historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
10 of 22 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesApple Intelligence on-device (2024 reference)
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2024-06-10Source for Release date (opens in a new tab)

Announcement date, not the later consumer rollout.

Parameters
Approximately 3B (2.58B non-embedding + 0.15B embedding)Source for Parameters (opens in a new tab)

Table 1 details the language decoder. The approximately 3B headline is rounded.

Architecture
26 layers; hidden size 3072; 24 query heads and 8 KV heads; head dimension 128Source for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected
Customization options
Apple-trained task adapters; no public self-service fine-tuning contract established for this generationSource for Customization options (opens in a new tab)
Deployment
On-device Apple siliconSource for Deployment (opens in a new tab)
Published price
Integrated product model; no standalone inference tariff verifiedSource for Published price (opens in a new tab)
Quantization and compression
Mixed 2/4-bit palettization, averaging 3.7 bits per weight; 3.5-bit variant also reportedSource for Quantization and compression (opens in a new tab)
Provider-reported latency
30 generated tokens/s and about 0.6 ms per prompt token on iPhone 15 ProSource for Provider-reported latency (opens in a new tab)

Provider measurement before token speculation; not an SLA or a 0.6 ms total first-token latency.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Apple Intelligence on-device (2024 reference)

Provider source (opens in a new tab)
API model ID
Not collected

Product or SDK model identity, not a verified public HTTP model selector.

Access
Historical product integration. No separately callable pinned checkpoint verified.
Regions
Supported Apple devices, OS versions, languages and regions only. A device-local model is not a guarantee of access in every market.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Apple Intelligence on-device (2024 reference)

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Apple documents this proprietary product model. No matching unrestricted public checkpoint was verified in the reviewed Apple weight inventory. Closed-weight classification is inferred for this product identity; OS delivery and member-gated model assets do not imply an open-weight release.

Classification evidence (opens in a new tab)

Lifecycle dates

Generation announced10 Jun 2024Source (opens in a new tab)

Sources reviewed